arXiv 2605.256032026-05-25cs.AI

通过电路引导的内外不一致性检测不忠实的思维链

Detecting Unfaithful Chain-of-Thought via Circuit-Guided Internal-External Discrepancy

Jilin University（吉林大学）；University of Central Florida（中央佛罗里达大学）；Arizona State University（亚利桑那州立大学）；University of Vienna（维也纳大学）；University of North Carolina at Chapel Hill（北卡罗来纳大学教堂山分校）

Xu Shen, Zhen Tan, Song Wang, Pingjun Hong, Rui Miao, Xin Wang, Tianlong Chen

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

提出CIE-Scorer框架，通过追踪句子级电路并利用Fused Gromov-Wasserstein距离度量内部与外部推理图的不一致性，实现实例级思维链不忠实检测，在FaithCoT-Bench上取得最优性能并降低电路构建成本。

摘要：

思维链（CoT）推理提高了大型语言模型（LLMs）的问题解决能力，但生成的推理轨迹可能并不忠实地反映模型的实际决策过程。现有的CoT不忠实检测器主要依赖于生成理由的外部信号，如文本合理性或答案一致性，而忽略了来自模型内部计算的证据。尽管最近的电路追踪方法通过追踪推理过程中信息如何在模型组件间流动提供了获取模型内部证据的途径，但为长CoT构建完整推理电路成本高昂且难以扩展。为应对这些挑战，我们提出了电路引导的内外不一致性评分器（CIE-Scorer），一个用于实例级CoT不忠实检测的框架。关键思想是，忠实的推理轨迹应与模型的计算过程一致，而不忠实的轨迹可能偏离它。CIE-Scorer从信息丰富的推理令牌中高效追踪紧凑的句子级电路，构建内部和外部推理图，并使用Fused Gromov-Wasserstein距离度量它们的不一致性。在FaithCoT-Bench的四个数据集上的实验表明，CIE-Scorer在降低电路构建成本的同时实现了最先进的性能，证明了将机械可解释性信号与外部推理轨迹相结合用于CoT不忠实检测的有效性。

英文摘要：

Chain-of-thought (CoT) reasoning improves the problem-solving ability of large language models (LLMs), but generated reasoning traces may not faithfully reflect the model's actual decision process. Existing CoT unfaithfulness detectors mainly rely on external signals from generated rationales, such as textual plausibility or answer consistency, while overlooking evidence from the model's internal computation. Although recent circuit tracing methods provide a way to obtain model-internal evidence by tracing how information flows through model components during reasoning, constructing full reasoning circuits for long CoTs is costly and difficult to scale. To address these challenges, we propose Circuit-guided Internal-External Discrepancy Scorer (CIE-Scorer), a framework for instance-level CoT unfaithfulness detection. The key idea is that faithful reasoning traces should align with the model's computational process, whereas unfaithful traces may diverge from it. CIE-Scorer efficiently traces compact sentence-level circuits from informative reasoning tokens, constructs internal and external reasoning graphs, and measures their discrepancy using Fused Gromov--Wasserstein distance. Experiments on four datasets from FaithCoT-Bench show that CIE-Scorer achieves state-of-the-art performance while reducing the cost of circuit construction, demonstrating the effectiveness of combining mechanistic interpretability signals with external reasoning traces for CoT unfaithfulness detection.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。